機器學習與分布式機器學習

超越最高精度 (Beyond Achieving Top Accuracy)

We are familiar with the idea of using machine learning to make predictions and inferences to high accuracies. This is after all a big part of what machine learning is expected to do.

我們熟悉使用機器學習對高精度進行預測和推斷的想法。 畢竟，這是機器學習所期望做的很大一部分。

Interestingly and importantly, we can leverage further on machine learning models. Beyond using the model to make top accuracy predictions, we can use it to create Uncertainty, Ambiguity or even Contention.

有趣且重要的是，我們可以進一步利用機器學習模型。 除了使用模型做出最高的準確性預測外，我們還可以使用它來創建不確定性，歧義甚至競爭。

我們不喜歡清晰和確定性嗎？ (Don’t We Like Clarity and Certainty?)

Not all the time. For good motivations,

并非一直如此。 為了好的動力

• Testers may want to create examples that are uncertain, so we can stress test a system for its result or even its decision on borderline inputs.
  測試人員可能想創建不確定的示例，因此我們可以對系統的結果甚至是對邊界輸入的決策進行壓力測試。
• Designers may be interested to visualise a hybrid prototype that combines existing products, but which we do not have a definite specification right now.
  設計人員可能想對結合了現有產品的混合原型進行可視化，但是我們目前尚無明確的規格。
• Trainers may want to create content that is ambiguous so that there are no straightforward answers, which therefore encourage participants to engage in debate.
  培訓人員可能希望創建含糊不清的內容，以便沒有簡單的答案，因此鼓勵參與者進行辯論。

The applications are plentiful.

應用程序很多。

真實的例子 (Real Example)

Let us use the MNIST dataset that contains images of the ten digits from 0 to 9. We then train a model to at least 98% accuracy, that is, a model that correctly predicts images to their corresponding digits at least 98% of the time.

讓我們使用包含從0到9的十個數字的圖像的MNIST數據集。然后，我們訓練一個模型至少達到98％的準確度，即，一個模型至少在98％的時間內正確地將圖像預測為其對應的數字。

Instead of stopping here, we further leverage on the model — we use the model to apply ambiguity to the digits.

除了在這里止步不前，我們進一步利用模型- 我們使用模型對數字應用歧義。

Let us confuse the digit “3” with “8”.

讓我們將數字“ 3”與“ 8”混淆。

The machine learning model filled in the blanks. It dotted two spots on the left of 3. Now, it is not unreasonable for a person to contend this 3 as an 8.

機器學習模型填補了空白。 它在3的左側點了兩個點。現在，一個人將3視為8并不是不合理的。

Let us confuse the digit “4” with “9”.

讓我們將數字“ 4”與“ 9”混淆。

The model attempted to build a roof over the 4 to make it closer to a 9. The model is conscious not to complete the entire roof as its goal is to make the digit uncertain between 4 and 9.

該模型試圖在4上建立屋頂以使其更接近9。該模型有意識地不完成整個屋頂，因為它的目標是使數字在4到9之間不確定。

Let us confuse the digit “6” with “5”.

讓我們將數字“ 6”與“ 5”混淆。

The model cut 6 in the middle and pulled out the resulting loose end to create the hook in 5. Additionally, it sketched a short stroke at the top of 6 to make it look like 5. It is now uncertain if the digit is 6 or 5.

模型在中間切出6，然后拉出產生的松動端，以在5中創建鉤子。此外，它還在6的頂部繪制了短筆畫以使其看起來像5。現在不確定數字是6還是5。 5，

模型是如何做到的？ (How does the Model Do It?)

By training the model to an accuracy of 98%, it has understood what digit images should look like. We could then ask it to engineer its knowledge and show us how digits that are uncertain, ambiguous or contentious look like.

通過將模型訓練到98％的準確度，它已經了解了數字圖像的外觀。 然后，我們可以要求它設計知識，并向我們展示不確定，模棱兩可或有爭議的數字。

For example, it is akin to asking “Could you create something that is in between “5” and “6” since you already know how they individually look like?”

例如，這類似于詢問“您是否可以創建介于“ 5”和“ 6”之間的內容，因為您已經知道它們的外觀？”

最后的想法 (Last Thoughts)

There are many good motivations for creating uncertainty, ambiguity or even contention, some of which have been explained above. Almost surely, there are also ways that uncertainty, ambiguity and contention can be used to harm or exploit! The following question probably gives us a better appreciation — could uncertain data be used as an attack against my automated system and cause it to produce an undesired decision?

產生不確定性，歧義甚至爭執的動機很多，上面已經解釋了其中的一些動機。 幾乎可以肯定，不確定性，模糊性和爭用還可以通過其他方式來損害或利用！ 以下問題可能會給我們帶來更好的理解-不確定的數據是否可以用作對我的自動化系統的攻擊，并導致產生不希望的決策？

翻譯自: https://medium.com/@ryyr/machine-learning-for-ambiguity-dbb99db613af

機器學習與分布式機器學習

總結

以上是生活随笔為你收集整理的机器学习与分布式机器学习_机器学习的歧义的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。